His research agenda is centered around establishing an LLM within a unified, safe, and scalable world model framework, thus enabling tight integration of System-1 (e.g., intuitive, fast, unconscious) and System-2 (e.g., slow, logical, conscious, algorithmic, planning) functionalities. More concretely:
Safe and Scalable System-2 Language Models: Human-AI Alignment, Reinforcement learning, Meta learning, Lifelong learning, Reasoning, Modular neural architectures, etc
Applications: Multi-modal learning (e.g., NLP, CV), Multi-modal embodied intelligence, AI for science, etc